Methods and apparatus for automated keyword refinement

1. A computer-implemented method, comprising: receiving text input, the text input including content associated with an input source; providing the text input to a keyword suggestion tool, wherein the keyword suggestion tool generates one or more keywords based on the text input; applying a text reduction function to the text input to generate a reduced text that is a subset of the text input, wherein the text reduction function is based on a term importance score of terms in the text input; providing the reduced text to the keyword suggestion tool, wherein the keyword suggestion tool generates one or more keywords based on the reduced text, the one or more keywords generated based on the reduced text generated independently from the one or more keywords generated based on the text input; and generating a keyword set output from a combination of the one or more keywords based on the text input and the one or more keywords based on the reduced text.

2. The computer-implemented method of claim 1 , wherein said generating further comprises: sorting the keyword set output according to a number of occurrences of a keyword of the keyword set output within the text input.

3. The computer-implemented method of claim 1 , wherein the text reduction function further comprises: calculating the term importance score for each term within the text input by determining a frequency of the term within the text input and by offsetting the term importance score by a frequency of the term within a corpus of input texts.

4. The computer-implemented method of claim 1 , wherein said applying the text reduction function comprises transmitting the text input across a network to a remote system and receiving the reduced text in response to said transmitting.

5. The computer-implemented method of claim 1 , wherein the text input is received periodically or aperiodically from a source feed.

6. The computer-implemented method of claim 1 , further comprising executing an advertisement object creation job, wherein the job comprises a specification for an input source feed for providing the text input; wherein the job comprises a specification enabling said generating the keyword set output; and wherein execution of the job comprises creating an advertisement object comprising the keyword set output.

7. A computer-implemented method, comprising: receiving text input; applying a text reduction function to the text input to generate a reduced text that is a subset of the text input, wherein the text reduction function is based on a term importance scoring of terms in the text input; and providing the reduced text to a keyword suggestion tool, wherein the keyword suggestion tool generates one or more keywords based on the reduced text; based on determining that an amount of the one or more keywords generated based on the reduced text does not satisfy a threshold amount of keywords, providing the text input to the keyword suggestion tool, wherein the keyword suggestion tool generates one or more keywords based on the text input; and returning a keyword set output.

8. The computer-implemented method of claim 7 , wherein said generating further comprises: sorting the keyword set output according to a number of occurrences of a keyword of the keyword set output within the input text.

9. A system, comprising: at least one processor; and a memory comprising program instructions, wherein the program instructions are executable by the at least one processor to: receive text input, the text input including content associated with an input source; provide the text input to a keyword suggestion tool, wherein the keyword suggestion tool generates one or more keywords based on the text input; apply a text reduction function to the text input to generate a reduced text that is a subset of the text input, wherein the text reduction function is based on a term importance score of terms in the text input; provide the reduced text to the keyword suggestion tool, wherein the keyword suggestion tool generates one or more keywords based on the reduced text, the one or more keywords generated based on the reduced text generated independently from the one or more keywords generated based on the text input; and generate a keyword set output from a combination of the one or more keywords based on the text input and the one or more keywords based on the reduced text.

10. The system of claim 9 , wherein the program instructions to generate the keyword set output are further executable by the at least one processor to: sort the keyword set output according to a number of occurrences of a keyword of the keyword set output within the text input.

11. The system of claim 9 , wherein the program instructions for the text reduction function are further executable by the at least one processor to: calculate the term importance score for each term within the text input by determining a frequency of the term within the text input and by offsetting the term importance score by a frequency of the term within a corpus of input texts.

12. The system of claim 9 , wherein the program instructions to apply the text reduction function are further executable by the at least one processor to: transmit the text input across a network to a remote system and receiving the reduced text in response to said transmission.

13. The system of claim 9 , wherein the program instructions to receive the text input are further executable by the at least one processor to: receive, periodically or aperiodically, the text input from a source feed.

14. A computer-readable storage medium storing program instructions, wherein the program instructions are computer-executable to implement: receiving text input, the text input including content associated with an input source; providing the text input to a keyword suggestion tool, wherein the keyword suggestion tool generates one or more keywords based on the text input; applying a text reduction function to the text input to generate a reduced text that is a subset of the text input, wherein the text reduction function is based on a term importance score of terms in the text input; providing the reduced text to the keyword suggestion tool, wherein the keyword suggestion tool generates one or more keywords based on the reduced text, the one or more keywords generated based on the reduced text generated independently from the one or more keywords generated based on the text input; and generating a keyword set output from a combination of the one or more keywords based on the text input and the one or more keywords based on the reduced text.

15. The computer-readable storage medium of claim 14 , wherein said generating further comprises: sorting the keyword set output according to a number of occurrences of a keyword of the keyword set output within the text input.

16. The computer-readable storage medium of claim 14 , wherein the text reduction function further comprises: calculating the term importance score for each term within the text input by determining a frequency of the term within the text input and by offsetting the term importance score by a frequency of the term within a corpus of input texts.

17. The computer-readable storage medium of claim 14 , wherein said applying the text reduction comprises transmitting the text input across a network to a remote system and receiving the reduced text in response to said transmitting.

18. The computer-readable storage medium of claim 14 , wherein the text input is received periodically or aperiodically from a source feed.

19. The computer-readable storage medium of claim 14 , wherein the program instructions further implement: executing an advertisement object creation job, wherein the job comprises a specification for an input source feed for providing the text input, wherein the job comprises a specification enabling said generating the keyword set output, and wherein execution of the job comprises creating an advertisement object comprising the keyword set output.